edit_figure

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the output_format parameter and gives examples of feedback, which is helpful, but it does not explain whether the original image is preserved, what prerequisites exist (e.g., existing image_path accessibility), or what the return value is. The description is not misleading but omits key behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with the core purpose stated in the first sentence, followed by one relevant parameter detail and practical examples. Every sentence earns its place, and the structure is front-loaded with the most important information. No fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has moderate complexity (4 params, no annotations, and an output schema is indicated but not detailed). The description covers the basic purpose and a key parameter, but it does not explain how this tool differs from multi_turn_edit, what image types are supported, or any operational constraints. It is adequate for a simple tool but not fully complete for an agent to confidently select it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has no descriptions (0% coverage), so the description must compensate. It does provide valuable detail for output_format ('Optional final raster delivery type such as png, gif, jpeg, or webp') and uses examples to illustrate the feedback format. However, the other three parameters (image_path, output_path, feedback) rely on self-explanatory names and receive no explicit clarification, leaving the compensation incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action ('Refine an academic figure') and the method ('using natural language feedback'). This distinguishes it from sibling tools like generate_figure (creation), verify_figure (validation), and composite_figure (combination), all of which have different verbs and resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is for refining existing figures with feedback, and the examples show the kind of natural language input expected. However, it does not explicitly state when to use this over siblings like multi_turn_edit, nor does it mention any exclusions or alternative tools. Usage context is present but not fully persuasive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.